Initial commit of converted ModernBERT model

config.json

@@ -0,0 +1,85 @@
+{
+  "allow_embedding_resizing": true,
+  "architectures": [
+    "ModernBertForMaskedLM"
+  ],
+  "attention_layer": "rope",
+  "attention_probs_dropout_prob": 0.0,
+  "attn_out_bias": false,
+  "attn_out_dropout_prob": 0.1,
+  "attn_qkv_bias": false,
+  "bert_layer": "prenorm",
+  "bos_token_id": 1,
+  "classifier_dropout": null,
+  "compile_model": true,
+  "decoder_bias": true,
+  "deterministic_fa2": false,
+  "embed_dropout_prob": 0.0,
+  "embed_norm": true,
+  "embedding_layer": "sans_pos",
+  "encoder_layer": "base",
+  "eos_token_id": 2,
+  "final_norm": true,
+  "global_attn_every_n_layers": 3,
+  "head_class_act": "silu",
+  "head_class_bias": false,
+  "head_class_dropout": 0.0,
+  "head_class_norm": false,
+  "head_pred_act": "gelu",
+  "head_pred_bias": false,
+  "head_pred_dropout": 0.0,
+  "head_pred_norm": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 384,
+  "init_cutoff_factor": 2.0,
+  "init_method": "full_megatron",
+  "init_small_embedding": false,
+  "init_std": 0.02,
+  "initial_attention_layer": null,
+  "initial_bert_layer": null,
+  "initial_mlp_layer": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-06,
+  "local_attn_rotary_emb_base": -1,
+  "local_attn_rotary_emb_dim": null,
+  "loss_function": "fa_cross_entropy",
+  "loss_kwargs": {
+    "reduction": "mean"
+  },
+  "mask_token_id": 38370,
+  "masked_prediction": true,
+  "max_position_embeddings": 1024,
+  "mlp_dropout_prob": 0.0,
+  "mlp_in_bias": false,
+  "mlp_layer": "glu",
+  "mlp_out_bias": false,
+  "model_type": "modernbert",
+  "norm_kwargs": {
+    "bias": false,
+    "eps": 1e-05
+  },
+  "normalization": "layernorm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 10,
+  "num_initial_layers": 1,
+  "pad_logits": false,
+  "pad_token_id": 38369,
+  "padding": "unpadded",
+  "pooling_type": "cls",
+  "position_embedding_type": "absolute",
+  "rotary_emb_base": 10000.0,
+  "rotary_emb_dim": 32,
+  "rotary_emb_interleaved": false,
+  "rotary_emb_scale_base": null,
+  "skip_first_prenorm": true,
+  "sliding_window": 128,
+  "transformers_version": "4.44.1",
+  "type_vocab_size": 2,
+  "unpad_embeddings": true,
+  "use_cache": true,
+  "use_fa2": true,
+  "use_sdpa_attn_mask": false,
+  "vocab_size": 38376
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:743f030b4a1b83fdf6c05ac925bbb7080ff24c4fc1665b55fc02e47d4681b91c
+size 136420746

special_tokens_map.json

@@ -0,0 +1,56 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,102 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "38365": {
+      "content": "<<SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38366": {
+      "content": "<</SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38367": {
+      "content": "[INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38368": {
+      "content": "[/INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38369": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "38370": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "legacy": true,
+  "mask_token": "<mask>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>",
+  "use_fast": true
+}